Yuqing Zhou
Author directory2026
WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
Yuqing Zhou | Zhuoer Wang | Jk | Hong Wang | Samson Koelle | Ziwei Zhu | Wei Niu
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Yuqing Zhou | Zhuoer Wang | Jk | Hong Wang | Samson Koelle | Ziwei Zhu | Wei Niu
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failures via environment-specific training or manual patching is costly and hard to scale. To enable self-evolving agents in user-facing service environments, we propose WISE-Flow, a workflow-centric framework that converts historical service interactions into reusable procedural experience by inducing workflows with prerequisite-augmented action blocks. At deployment, WISE-Flow aligns the agent’s execution trajectory to retrieved workflows and performs prerequisite-aware feasibility reasoning to achieve state-grounded next actions. Experiments on ToolSandbox and 𝜏2-bench show consistent improvement across base models.
COSE: Confidence-Orchestrated Self-Evolution for Effective LLM Reasoning
Bowen Wei | Nan Wang | Yuqing Zhou | Jinhao Pan | Ziwei Zhu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Bowen Wei | Nan Wang | Yuqing Zhou | Jinhao Pan | Ziwei Zhu
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. However, in many reasoning domains, the model must also validate generated tasks and judge generated answers to obtain training signals. This creates a training-signal challenge: erroneous self-judgments become erroneous gradient updates. Existing approaches either rely on external verifiers, which limits generality, or treat noisy self-generated feedback as supervision. We propose COSE (Confidence-Orchestrated Self-Evolution), which uses the LLM’s intrinsic confidence as a lightweight uncertainty signal to modulate learning. COSE introduces confidence-weighted PPO updates and confidence-prioritized replay. Across 19 held-out benchmarks and four Qwen/Llama backbones (0.6B–4B), COSE consistently improves over base models and achieves the best average performance in general reasoning and mathematics, while remaining competitive on code. Code and data are available at https://github.com/weibowen555/COSE_.
2025
Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
Yuqing Zhou | Ziwei Zhu
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Yuqing Zhou | Ziwei Zhu
Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when faced with out-of-distribution data where such spurious correlations no longer hold. To address this challenge, we propose the Causally Calibrated Robust Classifier (CCR), which aims to reduce models’ reliance on spurious correlations and improve model robustness. Our approach integrates a causal feature selection method based on counterfactual reasoning, along with an unbiased inverse propensity weighting (IPW) loss function. By focusing on selecting causal features, we ensure that the model relies less on spurious features during prediction. We theoretically justify our approach and empirically show that CCR achieves state-of-the-art performance among methods without group labels, and in some cases, it can compete with the models that utilize group labels. Our code can be found at: https://github.com/yuqing-zhou/Causal-Learning-For-Robust-Classifier.
2024
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
Yuqing Zhou | Ruixiang Tang | Ziyu Yao | Ziwei Zhu
Findings of the Association for Computational Linguistics: EMNLP 2024
Yuqing Zhou | Ruixiang Tang | Ziyu Yao | Ziwei Zhu
Findings of the Association for Computational Linguistics: EMNLP 2024
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model reliability beyond oversimplified shortcuts. We introduce a comprehensive benchmark that categorizes shortcuts into occurrence, style, and concept, aiming to explore the nuanced ways in which these shortcuts influence the performance of LMs. Through extensive experiments across traditional LMs, large language models, and state-of-the-art robust models, our research systematically investigates models’ resilience and susceptibilities to sophisticated shortcuts. Our benchmark and code can be found at: https://github.com/yuqing-zhou/shortcut-learning-in-text-classification.
Search